Long Short-Term Transformer for Online Action Detection

• URL: http://arxiv.org/abs/2107.03377v1
• Date: Wed, 7 Jul 2021 17:49:51 GMT
• Title: Long Short-Term Transformer for Online Action Detection
• Abstract summary: Long Short-term TRansformer (LSTR) is a new temporal modeling algorithm for online action detection. Compared to prior work, LSTR provides an effective and efficient method to model long videos with less algorithm design.
• Score: 96.23884916995978
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we present Long Short-term TRansformer (LSTR), a new temporal modeling algorithm for online action detection, by employing a long- and short-term memories mechanism that is able to model prolonged sequence data. It consists of an LSTR encoder that is capable of dynamically exploiting coarse-scale historical information from an extensively long time window (e.g., 2048 long-range frames of up to 8 minutes), together with an LSTR decoder that focuses on a short time window (e.g., 32 short-range frames of 8 seconds) to model the fine-scale characterization of the ongoing event. Compared to prior work, LSTR provides an effective and efficient method to model long videos with less heuristic algorithm design. LSTR achieves significantly improved results on standard online action detection benchmarks, THUMOS'14, TVSeries, and HACS Segment, over the existing state-of-the-art approaches. Extensive empirical analysis validates the setup of the long- and short-term memories and the design choices of LSTR.

Related papers

• EndPrompt: Efficient Long-Context Extension via Terminal Anchoring [62.81677226065374]
  We propose EndPrompt, a method that achieves effective context extension using only short training sequences.<n>We preserve the original short context as an intact first segment and append a brief terminal prompt as a second segment, assigning it positional indices near the target context length.<n>EndPrompt achieves an average RULER score of 76.03 and the highest average on LongBench, surpassing LCEG (72.24), LongLoRA (72.95), and full-length fine-tuning.
  arXiv  Detail & Related papers  (2026-05-14T09:00:03Z)
• Route Before Retrieve: Activating Latent Routing Abilities of LLMs for RAG vs. Long-Context Selection [57.3886742625188]
  Pre-Route is a proactive routing framework that performs structured reasoning before answering.<n>Our study shows three key findings: (i) LLMs possess latent routing ability that can be reliably elicited with guidelines; (ii) linear probes reveal that structured prompts sharpen the separability of the "optimal routing" in representation space; and (iii) distillation transfers this reasoning structure to smaller models for lightweight deployment.
  arXiv  Detail & Related papers  (2026-05-11T09:10:55Z)
• TimelineReasoner: Advancing Timeline Summarization with Large Reasoning Models [54.737142557469916]
  We propose TimelineReasoner, a framework that shifts Timeline Summarization from static generation to an active, reasoning-driven process.<n>We show that TimelineReasoner significantly outperforms existing LLM-based TLS methods in terms of timeline accuracy, coverage, and coherence.<n>This work not only pushes the boundaries of TLS but also highlights the broader potential of LRM-based reasoning frameworks for timeline summarization.
  arXiv  Detail & Related papers  (2026-04-03T12:30:15Z)
• LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards [57.993003392037174]
  LongR is a framework that enhances long-context performance by integrating a dynamic "Think-and-Read" mechanism.<n>LongR consistently enhances performance across diverse RL algorithms.
  arXiv  Detail & Related papers  (2026-02-05T15:26:47Z)
• Length-Adaptive Interest Network for Balancing Long and Short Sequence Modeling in CTR Prediction [50.094751096858204]
  LAIN is a plug-and-play framework that incorporates sequence length as a conditioning signal to balance long- and short-sequence modeling.<n>Our work offers a general, efficient, and deployable solution to mitigate length-induced bias in sequential recommendation.
  arXiv  Detail & Related papers  (2026-01-27T03:14:20Z)
• Hierarchical Document Refinement for Long-context Retrieval-augmented Generation [28.421675216147374]
  LongRefiner is an efficient plug-and-play refiner that leverages the inherent structural characteristics of long documents.<n>LongRefiner achieves competitive performance in various scenarios while using 10x fewer computational costs and latency compared to the best baseline.
  arXiv  Detail & Related papers  (2025-05-15T15:34:15Z)
• Balancing long- and short-term dynamics for the modeling of saliency in videos [14.527351636175615]
  We present a Transformer-based approach to learn a joint representation of video frames and past saliency information. Our model embeds long- and short-term information to detect dynamically shifting saliency in video.
  arXiv  Detail & Related papers  (2025-04-08T11:09:37Z)
• Online Dense Point Tracking with Streaming Memory [54.22820729477756]
  Dense point tracking is a challenging task requiring the continuous tracking of every point in the initial frame throughout a substantial portion of a video.<n>Recent point tracking algorithms usually depend on sliding windows for indirect information propagation from the first frame to the current one.<n>We present a lightweight and fast model with textbfStreaming memory for dense textbfPOint textbfTracking and online video processing.
  arXiv  Detail & Related papers  (2025-03-09T06:16:49Z)
• Breaking the Context Bottleneck on Long Time Series Forecasting [6.36010639533526]
  Long-term time-series forecasting is essential for planning and decision-making in economics, energy, and transportation. Recent advancements have enhanced the efficiency of these models, but the challenge of effectively leveraging longer sequences persists. We propose the Logsparse Decomposable Multiscaling (LDM) framework for the efficient and effective processing of long sequences.
  arXiv  Detail & Related papers  (2024-12-21T10:29:34Z)
• LOGO -- Long cOntext aliGnment via efficient preference Optimization [29.510993993980573]
  LOGO(Long cOntext aliGnment via efficient preference optimization) is a training strategy that first introduces preference optimization for long-context alignment. By training with only 0.3B data on a single 8$times$A800 GPU machine for 16 hours, LOGO allows the Llama-3-8B-Instruct-80K model to achieve comparable performance with GPT-4.
  arXiv  Detail & Related papers  (2024-10-24T08:27:26Z)
• Forgetting Curve: A Reliable Method for Evaluating Memorization Capability for Long-context Models [58.6172667880028]
  We propose a new method called forgetting curve to measure the memorization capability of long-context models. We show that forgetting curve has the advantage of being robust to the tested corpus and the experimental settings. Our measurement provides empirical evidence for the effectiveness of transformer extension techniques while raises questions for the effective length of RNN/SSM based models.
  arXiv  Detail & Related papers  (2024-10-07T03:38:27Z)
• LongSkywork: A Training Recipe for Efficiently Extending Context Length in Large Language Models [61.12177317970258]
  LongSkywork is a long-context Large Language Model capable of processing up to 200,000 tokens. We develop two novel methods for creating synthetic data. LongSkywork achieves outstanding performance on a variety of long-context benchmarks.
  arXiv  Detail & Related papers  (2024-06-02T03:34:41Z)
• Bidirectional Long-Range Parser for Sequential Data Understanding [3.76054468268713]
  We introduce BLRP (Bidirectional Long-Range), a novel and versatile attention mechanism designed to increase performance and efficiency on long-sequence tasks. We show the benefits and versatility of our approach on vision and language domains by demonstrating competitive results against state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-04-08T05:45:03Z)
• Effective Long-Context Scaling of Foundation Models [90.57254298730923]
  We present a series of long-context LLMs that support effective context windows of up to 32,768 tokens. Our models achieve consistent improvements on most regular tasks and significant improvements on long-context tasks over Llama 2.
  arXiv  Detail & Related papers  (2023-09-27T21:41:49Z)
• Efficient Long-Short Temporal Attention Network for Unsupervised Video Object Segmentation [23.645412918420906]
  Unsupervised Video Object (VOS) aims at identifying the contours of primary foreground objects in videos without any prior knowledge. Previous methods do not fully use spatial-temporal context and fail to tackle this challenging task in real-time. This motivates us to develop an efficient Long-Short Temporal Attention network (termed LSTA) for unsupervised VOS task from a holistic view.
  arXiv  Detail & Related papers  (2023-09-21T01:09:46Z)
• A Novel Long-term Iterative Mining Scheme for Video Salient Object Detection [54.53335983750033]
  Short-term methodology conflicts with the real mechanism of our visual system. This paper proposes a novel VSOD approach, which performs VSOD in a complete long-term way. The proposed approach outperforms almost all SOTA models on five widely used benchmark datasets.
  arXiv  Detail & Related papers  (2022-06-20T04:27:47Z)
• Long-Short Temporal Modeling for Efficient Action Recognition [32.159784061961886]
  We propose a new two-stream action recognition network, termed as MENet, consisting of a Motion Enhancement (ME) module and a Video-level Aggregation (VLA) module. For short-term motions, we design an efficient ME module to enhance the short-term motions by mingling the motion saliency among neighboring segments. As for long-term aggregations, VLA is adopted at the top of the appearance branch to integrate the long-term dependencies across all segments.
  arXiv  Detail & Related papers  (2021-06-30T02:54:13Z)
• Finding Action Tubes with a Sparse-to-Dense Framework [62.60742627484788]
  We propose a framework that generates action tube proposals from video streams with a single forward pass in a sparse-to-dense manner. We evaluate the efficacy of our model on the UCF101-24, JHMDB-21 and UCFSports benchmark datasets.
  arXiv  Detail & Related papers  (2020-08-30T15:38:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.